Legal claims defining the scope of protection, as filed with the USPTO.
4. The method of claim 3, wherein a mistake earlier in a prediction path has a higher penalty than a mistake later in the prediction path.
5. The method of claim 2, wherein a mistake in the sequence prediction model has a lesser penalty when less data is available and a greater penalty when more data is available.
6. The method of claim 1, wherein the summarizing uses natural language processing to encode the touchpoints into feature vectors.
7. The method of claim 1, further comprising mapping the feature vectors to the embedding layer.
11. The computer program product of claim 10, wherein a mistake earlier in a prediction path has a higher penalty than a mistake later in the prediction path.
12. The computer program product of claim 9, wherein a mistake in the sequence prediction model has a lesser penalty when less data is available and a greater penalty when more data is available.
13. The computer program product of claim 8, wherein the summarizing uses natural language processing to encode the touchpoints into feature vectors.
14. The computer program product of claim 8, further comprising mapping the feature vectors to the embedding layer.
18. The system of claim 17, wherein a mistake earlier in a prediction path has a higher penalty than a mistake later in the prediction path.
19. The system of claim 16, wherein a mistake in the sequence prediction model has a lesser penalty when less data is available and a greater penalty when more data is available.
20. The system of claim 15, wherein the summarizing uses natural language processing to encode the touchpoints into feature vectors.
Unknown
November 12, 2024
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.